Real-time and Large-scale Fleet Allocation of Autonomous Taxis: A Case Study in New York Manhattan Island

TL;DR

This paper presents a novel fleet allocation model for autonomous taxis using Constrained Multi-agent Markov Decision Processes and a Column Generation algorithm, significantly improving efficiency and profit in large-scale, real-time scenarios.

Contribution

It introduces a scalable, optimal fleet allocation framework combining CMMDP and Column Generation for autonomous taxis, addressing supply-demand imbalance and operational costs.

Findings

Achieved 12.40% increase in individual efficiency

Realized 6.54% rise in income and utilization

Platform profit improved by 4.59%

Abstract

Nowadays, autonomous taxis become a highly promising transportation mode, which helps relieve traffic congestion and avoid road accidents. However, it hinders the wide implementation of this service that traditional models fail to efficiently allocate the available fleet to deal with the imbalance of supply (autonomous taxis) and demand (trips), the poor cooperation of taxis, hardly satisfied resource constraints, and on-line platform's requirements. To figure out such urgent problems from a global and more farsighted view, we employ a Constrained Multi-agent Markov Decision Processes (CMMDP) to model fleet allocation decisions, which can be easily split into sub-problems formulated as a 'Dynamic assignment problem' combining both immediate rewards and future gains. We also leverage a Column Generation algorithm to guarantee the efficiency and optimality in a large scale. Through extensive experiments, the proposed approach not only achieves remarkable improvements over the state-of-the-art benchmarks in terms of the individual's efficiency (arriving at 12.40%, 6.54% rise of income and utilization, respectively) and the platform's profit (reaching 4.59% promotion) but also reveals a time-varying fleet adjustment policy to minimize the operation cost of the platform.